Gasol Sun

ToG. [ICLR 2024] Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

Iter-CoT. [NAACL 2024] Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models

DynamicRAG. [NeurIPS 2025] Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

GRACE. [ICLR 2025] Official repo for paper: "GRACE: Generative Representation Learning via Contrastive Policy Optimization"

NanoRAG. Simple implementation of Retrieval-Augmented Generation System

pixiu. 貔貅(PiXiu): 基于中文金融知识图谱的指令微调模型

PyRAG. Retrieval is CheapShow Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation

MVP. Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning

SURf. [EMNLP 2024] SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information

APOLLO. [COLING 2024] APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning

BAR-RAG. [ICML 2026] Official repo for paper: "Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation"